© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 33863
    Prev
    Next
    INDEX
    Explanations

    mis followed by words indicating error or wrongness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wend
    -0.10
    ein
    -0.09
    tran
    -0.09
     Corm
    -0.08
    orate
    -0.08
    isé
    -0.08
     positive
    -0.08
    unya
    -0.08
     Positive
    -0.07
    ondere
    -0.07
    POSITIVE LOGITS
    chie
    0.17
    direction
    0.15
    direct
    0.15
    named
    0.15
    interpret
    0.14
    interpre
    0.13
    management
    0.13
    aligned
    0.13
    interpreted
    0.13
    beg
    0.12
    Activations Density 0.008%

    No Known Activations